Skip to main content

NanoGPT MCP Integration

The NanoGPT MCP (Model Context Protocol) server allows you to use NanoGPT’s AI capabilities directly from MCP-compatible clients like Claude Code, Cursor, and other AI coding assistants.

Features

The NanoGPT MCP server provides these tools: Each tool describes its parameters to your agent through MCP, so the agent can call it without reading the API documentation. The source code is on GitHub.

Prerequisites

  • A NanoGPT account with an API key (get one here)
  • Node.js 22.x or later
  • An MCP-compatible client (Claude Code, Codex, Cursor, Claude Desktop, etc.)

Installation

The easiest way to use the NanoGPT MCP server is via npx.

Claude Code

macOS / Linux
Windows
On native Windows, npx is usually a .cmd shim, so it should be launched through cmd /c. If you use WSL, run the macOS/Linux command inside WSL instead of the native Windows one. Claude Code’s MCP CLI syntax has changed over time. If you copied an older NanoGPT command, remove the existing nanogpt MCP entry and add it again using the commands on this page. An immediate Invalid API key error can be caused by a broken MCP launcher command, not just a bad key value.

Codex

Cursor, Claude Desktop and other JSON-configured clients

Replace YOUR_API_KEY with your actual NanoGPT API key.

Option 2: Global Installation

Then add to your MCP client:

Configuration

Required Environment Variables

Optional Environment Variables

Set NANOGPT_DEFAULT_MODEL=anthropic/claude-sonnet-5.5 in your MCP client configuration to use Claude Sonnet 5.5 for chat requests that omit model.

Usage Examples

Once configured, you can use NanoGPT tools directly from your MCP client. Here are some examples:

Check Your Balance

Ask your AI assistant:
“Check my NanoGPT balance”
The assistant will call nanogpt_get_balance and show your USD and Nano balances.

Chat with AI Models

“Use NanoGPT to ask Claude Sonnet about the best practices for REST API design”

Generate Images

“Use NanoGPT to generate an image of a futuristic city at sunset”

Analyze Images

“Use NanoGPT vision to analyze this product photo”

Search the Web

“Use NanoGPT web search to find the latest news about AI”

Generate Videos

“Use NanoGPT to generate a 5 second video of a paper boat drifting on a calm pond”

Generate 3D Models

“Use NanoGPT to make a 3D model of a wooden rocking chair and give me the GLB link”

Get YouTube Transcripts

“Use NanoGPT to get the transcript of this YouTube video: https://www.youtube.com/watch?v=…”

Scrape Web Pages

“Use NanoGPT to scrape the content from https://example.com”

Tool Reference

nanogpt_chat

Send a chat completion request to an AI model. Parameters:
  • messages (required): Array of message objects with role (“system”, “user”, “assistant”) and content
  • model (optional): Model ID (uses NANOGPT_DEFAULT_MODEL when omitted)
  • temperature (optional): Sampling temperature (0-2)
  • max_tokens (optional): Maximum tokens in response
Example:

nanogpt_get_balance

Check your current account balance. Parameters: None Returns:
  • usd_balance: Balance in USD
  • nano_balance: Balance in Nano (XNO)
  • nanoDepositAddress: Your Nano deposit address

nanogpt_image_generate

Generate images from text prompts. Parameters:
  • prompt (required): Text description of the image to generate
  • model (optional): Image model to use (e.g., “openai/gpt-image-2.5/flare/text-to-image”)
  • n (optional): Number of images to generate (1-10)
  • size (optional): Image size (e.g., “1024x1024”)
  • quality (optional): Image quality setting
Example:
Search the web for current information. Parameters:
  • query (required): Search query
  • depth (optional): “standard” or “deep”
  • outputType (optional): “searchResults”, “sourcedAnswer”, or “structured”
  • includeImages (optional): Include image results
  • fromDate / toDate (optional): Date range filter (YYYY-MM-DD)
Example:

nanogpt_vision

Analyze images using vision-capable models. Parameters:
  • messages (required): Array of message objects with text and image content blocks
  • model (optional): Vision-capable model ID
  • temperature (optional): Sampling temperature (0-2)
  • max_tokens (optional): Maximum tokens in response
Example:

nanogpt_scrape_urls

Scrape content from web pages. Parameters:
  • urls (required): Array of URLs to scrape (max 5 per request)
  • mode (optional): “scrape-page” or “conversation”
  • stealthMode (optional): Use stealth mode for scraping
Example:

nanogpt_youtube_transcribe

Get transcripts from YouTube videos. Parameters:
  • urls (required): Array of YouTube URLs (max 10 per request)
Example:

nanogpt_video_generate

Generate videos from a text prompt, an image or a video. Parameters:
  • operation (optional): submit (default), submit_and_poll, poll or status
  • model (required to submit): Video model ID from nanogpt_list_video_models
  • prompt (optional): Text description of the video
  • imageUrl / imageDataUrl (optional): Input image as a public URL or data URL
  • duration, resolution, aspect_ratio (optional): Model-dependent settings
  • runId (for poll and status): Job ID returned by a previous call
  • timeout_ms (optional): How long to wait for the result (default 50000)
Example:

nanogpt_3d_generate

Generate a 3D model (GLB and other formats) from a text prompt or an image. Parameters:
  • operation (optional): submit_and_poll (default), submit, poll or status
  • model (required to submit): 3D model ID from nanogpt_list_3d_models
  • prompt (optional): Text description for text-to-3D models
  • imageUrl / imageDataUrl (optional): Input image for image-to-3D models
  • runId (for poll and status): Job ID returned by a previous call
  • timeout_ms (optional): How long to wait for the result (default 50000)
Example:

Video and 3D jobs

Video and 3D jobs run asynchronously and usually take between 30 seconds and several minutes:
  • operation: "submit_and_poll" submits the job and waits up to timeout_ms (default 50 seconds) for the result. A finished job returns the video or GLB URL. The wait includes the submit request, but a submission that is still in progress is never cut short (aborting it could lose a job that was already accepted), so an unusually slow submission can take longer than timeout_ms.
  • If the job is still running, the result contains its runId. Call the tool again with operation: "poll" and that runId to keep waiting, or operation: "status" for a single check.
  • operation: "submit" only submits the job.
Many MCP clients stop a tool call after 60 seconds, so keep timeout_ms below your client’s tool timeout and continue long jobs with poll. A job is charged when it is submitted, so poll instead of submitting it again.

Other tools

Image editing, speech, music, transcription, embeddings, AI detection, artistic QR codes, and the research and data tools follow the same pattern: the agent sees each tool’s parameters through MCP.

nanogpt_list_text_models

List available text/chat models. Parameters:
  • detailed (optional): Include pricing information (default: false)

nanogpt_list_image_models

List available image generation models. Parameters:
  • detailed (optional): Include pricing information (default: true)

nanogpt_list_audio_models

List available audio models. Parameters:
  • detailed (optional): Include pricing information (default: true)
  • type (optional): Filter by type: “tts”, “stt”, or “all”

nanogpt_list_video_models

List available video generation models. Parameters:
  • detailed (optional): Include pricing information (default: true)

nanogpt_list_3d_models

List available 3D generation models with pricing and whether each accepts text, images or both. Parameters:
  • detailed (optional): Include pricing information (default: true)

Resources

Resources allow agents to access data saved during a session:
  • nanogpt://raw/{id}: Raw JSON response from a previous API call
  • nanogpt://image/{id}: Generated images stored during the session
  • nanogpt://media/{id}: Generated audio and other media stored during the session

Error Handling

The MCP server provides clear error messages for common issues:

Billing

  • All paid tools deduct from your NanoGPT balance
  • Use nanogpt_get_balance to check your balance before expensive operations
  • Model listing tools are free to use
  • Video and 3D jobs are charged when submitted; use poll to keep waiting instead of submitting again

Troubleshooting

”Missing required env var: NANOGPT_API_KEY”

macOS / Linux
Windows
Make sure you set your API key when adding the MCP server. If you re-add the server later, include --env NANOGPT_API_KEY=... again.

”Invalid API key” errors

An immediate Invalid API key error can be caused by a broken MCP launcher command, not just a bad key value.
  1. Verify your API key at nano-gpt.com/api
  2. Make sure you’re using the full API key value
  3. Check for extra spaces or newlines in the key
  4. Verify that your Claude Code MCP launch command is correct, especially on Windows where npx should be run via cmd /c "C:\Program Files\nodejs\npx.cmd".

Requests timing out

For long-running operations like web search, you can increase the timeout: macOS / Linux
Windows

Video or 3D tool calls time out

Many MCP clients stop a tool call after 60 seconds. Keep timeout_ms below that limit and continue with operation: "poll" and the returned runId until the job finishes.

MCP server not connecting

  1. Ensure Node.js 22+ is installed: node --version
  2. Try removing and re-adding the MCP server
  3. Check your MCP client’s logs for detailed error messages
  4. If you already added NanoGPT using an older command, remove the existing nanogpt MCP entry and add it again with the updated command

Support

Privacy & Security

  • Your API key is stored locally and only sent to NanoGPT servers
  • The MCP server runs locally on your machine
  • No data is logged or stored by the MCP server
  • Chat messages and other content are processed according to NanoGPT’s privacy policy